188 lines
9.9 KiB
YAML
188 lines
9.9 KiB
YAML
{{- /*
|
|
Generated from 'kubernetes-system-kubelet' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
|
|
Do not change in-place! In order to change this file first read following link:
|
|
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
|
|
*/ -}}
|
|
{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}
|
|
{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesSystem }}
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-system-kubelet" | trunc 63 | trimSuffix "-" }}
|
|
namespace: {{ template "kube-prometheus-stack.namespace" . }}
|
|
labels:
|
|
app: {{ template "kube-prometheus-stack.name" . }}
|
|
{{ include "kube-prometheus-stack.labels" . | indent 4 }}
|
|
{{- if .Values.defaultRules.labels }}
|
|
{{ toYaml .Values.defaultRules.labels | indent 4 }}
|
|
{{- end }}
|
|
{{- if .Values.defaultRules.annotations }}
|
|
annotations:
|
|
{{ toYaml .Values.defaultRules.annotations | indent 4 }}
|
|
{{- end }}
|
|
spec:
|
|
groups:
|
|
- name: kubernetes-system-kubelet
|
|
rules:
|
|
- alert: KubeNodeNotReady
|
|
annotations:
|
|
description: '{{`{{`}} $labels.node {{`}}`}} has been unready for more than 15 minutes.'
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubenodenotready
|
|
summary: Node is not ready.
|
|
expr: kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeNodeUnreachable
|
|
annotations:
|
|
description: '{{`{{`}} $labels.node {{`}}`}} is unreachable and some workloads may be rescheduled.'
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubenodeunreachable
|
|
summary: Node is unreachable.
|
|
expr: (kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} unless ignoring(key,value) kube_node_spec_taint{job="kube-state-metrics",key=~"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn"}) == 1
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeletTooManyPods
|
|
annotations:
|
|
description: Kubelet '{{`{{`}} $labels.node {{`}}`}}' is running at {{`{{`}} $value | humanizePercentage {{`}}`}} of its Pod capacity.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubelettoomanypods
|
|
summary: Kubelet is running at capacity.
|
|
expr: |-
|
|
count by(node) (
|
|
(kube_pod_status_phase{job="kube-state-metrics",phase="Running"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job="kube-state-metrics"})
|
|
)
|
|
/
|
|
max by(node) (
|
|
kube_node_status_capacity_pods{job="kube-state-metrics"} != 1
|
|
) > 0.95
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeNodeReadinessFlapping
|
|
annotations:
|
|
description: The readiness status of node {{`{{`}} $labels.node {{`}}`}} has changed {{`{{`}} $value {{`}}`}} times in the last 15 minutes.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubenodereadinessflapping
|
|
summary: Node readiness status is flapping.
|
|
expr: sum(changes(kube_node_status_condition{status="true",condition="Ready"}[15m])) by (node) > 2
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeletPlegDurationHigh
|
|
annotations:
|
|
description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletplegdurationhigh
|
|
summary: Kubelet Pod Lifecycle Event Generator is taking too long to relist.
|
|
expr: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeletPodStartUpLatencyHigh
|
|
annotations:
|
|
description: Kubelet Pod startup 99th percentile latency is {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletpodstartuplatencyhigh
|
|
summary: Kubelet Pod startup latency is too high.
|
|
expr: histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeletClientCertificateExpiration
|
|
annotations:
|
|
description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletclientcertificateexpiration
|
|
summary: Kubelet client certificate is about to expire.
|
|
expr: kubelet_certificate_manager_client_ttl_seconds < 604800
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeletClientCertificateExpiration
|
|
annotations:
|
|
description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletclientcertificateexpiration
|
|
summary: Kubelet client certificate is about to expire.
|
|
expr: kubelet_certificate_manager_client_ttl_seconds < 86400
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeletServerCertificateExpiration
|
|
annotations:
|
|
description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletservercertificateexpiration
|
|
summary: Kubelet server certificate is about to expire.
|
|
expr: kubelet_certificate_manager_server_ttl_seconds < 604800
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeletServerCertificateExpiration
|
|
annotations:
|
|
description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletservercertificateexpiration
|
|
summary: Kubelet server certificate is about to expire.
|
|
expr: kubelet_certificate_manager_server_ttl_seconds < 86400
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeletClientCertificateRenewalErrors
|
|
annotations:
|
|
description: Kubelet on node {{`{{`}} $labels.node {{`}}`}} has failed to renew its client certificate ({{`{{`}} $value | humanize {{`}}`}} errors in the last 5 minutes).
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletclientcertificaterenewalerrors
|
|
summary: Kubelet has failed to renew its client certificate.
|
|
expr: increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: KubeletServerCertificateRenewalErrors
|
|
annotations:
|
|
description: Kubelet on node {{`{{`}} $labels.node {{`}}`}} has failed to renew its server certificate ({{`{{`}} $value | humanize {{`}}`}} errors in the last 5 minutes).
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletservercertificaterenewalerrors
|
|
summary: Kubelet has failed to renew its server certificate.
|
|
expr: increase(kubelet_server_expiration_renew_errors[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- if .Values.prometheusOperator.kubeletService.enabled }}
|
|
- alert: KubeletDown
|
|
annotations:
|
|
description: Kubelet has disappeared from Prometheus target discovery.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletdown
|
|
summary: Target disappeared from Prometheus target discovery.
|
|
expr: absent(up{job="kubelet", metrics_path="/metrics"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- end }} |